{"dcterms:modified":"2024-01-18","dcterms:creator":"heiDATA","@type":"ore:ResourceMap","schema:additionalType":"Dataverse OREMap Format v1.0.0","dvcore:generatedBy":{"@type":"schema:SoftwareApplication","schema:name":"Dataverse","schema:version":"6.1 build 1590-f5d1299","schema:url":"https://github.com/iqss/dataverse"},"@id":"https://heidata.uni-heidelberg.de/api/datasets/export?exporter=OAI_ORE&persistentId=https://doi.org/10.11588/data/0Z7H1X","ore:describes":{"publication":{"publicationCitation":"Miriam Kesselmeier, Justo Lorenzo Bermejo; Robust logistic regression to narrow down the winner’s curse for rare and recessive susceptibility variants, Briefings in Bioinformatics, Volume 18, Issue 6, 1 November 2017, Pages 962–972","publicationIDType":"doi","publicationIDNumber":"10.1093/bib/bbw074","publicationURL":"https://doi.org/10.1093/bib/bbw074"},"citation:keyword":[{"citation:keywordValue":"robust logistic regression"},{"citation:keywordValue":"re-descending Hampel function"},{"citation:keywordValue":"winner’s curse"},{"citation:keywordValue":"genetic association study"}],"citation:datasetContact":{"citation:datasetContactName":"Lorenzo Bermejo, Justo","citation:datasetContactAffiliation":"Institute of Medical Biometry and Informatics, University of Heidelberg, Heidelberg, Germany","citation:datasetContactEmail":"lorenzo@imbi.uni-heidelberg.de"},"author":[{"citation:authorName":"Kesselmeier, Miriam","citation:authorAffiliation":"Institute of Medical Biometry and Informatics, University Hospital Heidelberg, Heidelberg, Germany and Clinical Epidemiology, Center for Sepsis Control and Care (CSCC), Jena University Hospital, Jena, Germany"},{"citation:authorName":"Lorenzo Bermejo, Justo","citation:authorAffiliation":"Institute of Medical Biometry and Informatics, University of Heidelberg, Heidelberg, Germany","authorIdentifierScheme":"ORCID","authorIdentifier":"http://orcid.org/0000-0002-6568-5333"}],"citation:dsDescription":{"citation:dsDescriptionValue":"Logistic regression is the most common technique used for genetic case-control association studies. A disadvantage of standard maximum likelihood estimators of the genotype relative risk (GRR) is their strong dependence on outlier subjects, for example, patients diagnosed at unusually young age. Robust methods are available to constrain outlier influence, but they are scarcely used in genetic studies. This article provides a non-intimidating introduction to robust logistic regression, and investigates its benefits and limitations in genetic association studies. We applied the bounded Huber and extended the R package ‘robustbase’ with the re-descending Hampel functions to down-weight outlier influence. Computer simulations were carried out to assess the type I error rate, mean squared error (MSE) and statistical power according to major characteristics of the genetic study and investigated markers. Simulations were complemented with the analysis of real data. Both standard and robust estimation controlled type I error rates. Standard logistic regression showed the highest power but standard GRR estimates also showed the largest bias and MSE, in particular for associated rare and recessive variants. For illustration, a recessive variant with a true GRR=6.32 and a minor allele frequency=0.05 investigated in a 1000 case/1000 control study by standard logistic regression resulted in power=0.60 and MSE=16.5. The corresponding figures for Huber-based estimation were power=0.51 and MSE=0.53. Overall, Hampel- and Huber-based GRR estimates did not differ much. Robust logistic regression may represent a valuable alternative to standard maximum likelihood estimation when the focus lies on risk prediction rather than identification of susceptibility variants."},"dateOfDeposit":"2018-07-20","subject":"Medicine, Health and Life Sciences","title":"Robust logistic regression to narrow down the winner's curse for rare and recessive susceptibility variants [Source Code]","software":{"citation:softwareName":"R"},"@id":"https://doi.org/10.11588/data/0Z7H1X","@type":["ore:Aggregation","schema:Dataset"],"schema:version":"1.0","schema:name":"Robust logistic regression to narrow down the winner's curse for rare and recessive susceptibility variants [Source Code]","schema:dateModified":"Mon Oct 15 10:33:07 CEST 2018","schema:datePublished":"2018-10-15","schema:creativeWorkStatus":"RELEASED","dvcore:termsOfUse":"Source code is licensed under General Public License v3 (GPL v3).","dvcore:fileTermsOfAccess":{"dvcore:fileRequestAccess":false},"schema:includedInDataCatalog":"heiDATA","schema:isPartOf":{"schema:name":"Statistical Genetics","@id":"https://heidata.uni-heidelberg.de/dataverse/statistical-genetics","schema:description":"Data publications from the Statistical Genetics Group at Heidelberg University's Institute of Medical Biometry and Informatics.","schema:isPartOf":{"schema:name":"heiDATA","@id":"https://heidata.uni-heidelberg.de/dataverse/root","schema:description":"heiDATA is an institutional repository for Open Research Data from Heidelberg University. It is managed by the Competence Centre for Research Data, a joint institution of the University Library and the Computing Centre. If you are interested in publishing your data here, please have a look at our user guide and get in touch with us. Detailed information on heiDATA can be found in our service description."}},"ore:aggregates":[{"schema:name":"Robust logistic regression to narrow down Supplement_3.docx","dvcore:restricted":false,"schema:version":4,"dvcore:datasetVersionId":320,"dvcore:categories":["Code"],"@id":"doi:10.11588/data/0Z7H1X/B7XDU8","schema:sameAs":"https://heidata.uni-heidelberg.de/api/access/datafile/:persistentId?persistentId=doi:10.11588/data/0Z7H1X/B7XDU8","@type":"ore:AggregatedResource","schema:fileFormat":"application/vnd.openxmlformats-officedocument.wordprocessingml.document","dvcore:filesize":90535,"dvcore:storageIdentifier":"file://16676687e55-5187689097e7","dvcore:rootDataFileId":-1,"dvcore:checksum":{"@type":"MD5","@value":"d3828960b320592e44fa870b04bb750b"}},{"schema:name":"Source_Code_Robust_Logistic_Regression_to_Narrow_Down_the_Winners_Curse.pdf","dvcore:restricted":false,"schema:version":1,"dvcore:datasetVersionId":320,"dvcore:categories":["Code"],"@id":"doi:10.11588/data/0Z7H1X/HV2MBK","schema:sameAs":"https://heidata.uni-heidelberg.de/api/access/datafile/:persistentId?persistentId=doi:10.11588/data/0Z7H1X/HV2MBK","@type":"ore:AggregatedResource","schema:fileFormat":"application/pdf","dvcore:filesize":119598,"dvcore:storageIdentifier":"file://164b832ea0b-e32732b0a953","dvcore:rootDataFileId":-1,"dvcore:checksum":{"@type":"MD5","@value":"40c189590f4db725e93d70df7636c741"}}],"schema:hasPart":["doi:10.11588/data/0Z7H1X/B7XDU8","doi:10.11588/data/0Z7H1X/HV2MBK"]},"@context":{"author":"http://purl.org/dc/terms/creator","authorIdentifier":"http://purl.org/spar/datacite/AgentIdentifier","authorIdentifierScheme":"http://purl.org/spar/datacite/AgentIdentifierScheme","citation":"https://dataverse.org/schema/citation/","dateOfDeposit":"http://purl.org/dc/terms/dateSubmitted","dcterms":"http://purl.org/dc/terms/","dvcore":"https://dataverse.org/schema/core#","ore":"http://www.openarchives.org/ore/terms/","publication":"http://purl.org/dc/terms/isReferencedBy","publicationCitation":"http://purl.org/dc/terms/bibliographicCitation","publicationIDNumber":"http://purl.org/spar/datacite/ResourceIdentifier","publicationIDType":"http://purl.org/spar/datacite/ResourceIdentifierScheme","publicationURL":"https://schema.org/distribution","schema":"http://schema.org/","software":"https://www.w3.org/TR/prov-o/#wasGeneratedBy","subject":"http://purl.org/dc/terms/subject","title":"http://purl.org/dc/terms/title"}}